Skeletal Muscle Segmentation at the Level of the Third Lumbar Vertebra (L3) in Low-Dose Computed Tomography: A Lightweight Algorithm

Background: The cross-sectional area of skeletal muscles at the level of the third lumbar vertebra (L3) measured from computed tomography (CT) images is an established imaging biomarker used to assess patients’ nutritional status. With the increasing prevalence of low-dose CT scans in clinical pract...

Full description

Saved in:
Bibliographic Details
Main Authors: Xuzhi Zhao, Yi Du, Haizhen Yue
Format: Article
Language:English
Published: MDPI AG 2024-09-01
Series:Tomography
Subjects:
Online Access:https://www.mdpi.com/2379-139X/10/9/111
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850259286790242304
author Xuzhi Zhao
Yi Du
Haizhen Yue
author_facet Xuzhi Zhao
Yi Du
Haizhen Yue
author_sort Xuzhi Zhao
collection DOAJ
description Background: The cross-sectional area of skeletal muscles at the level of the third lumbar vertebra (L3) measured from computed tomography (CT) images is an established imaging biomarker used to assess patients’ nutritional status. With the increasing prevalence of low-dose CT scans in clinical practice, accurate and automated skeletal muscle segmentation at the L3 level in low-dose CT images has become an issue to address. This study proposed a lightweight algorithm for automated segmentation of skeletal muscles at the L3 level in low-dose CT images. Methods: This study included 57 patients with rectal cancer, with both low-dose plain and contrast-enhanced pelvic CT image series acquired using a radiotherapy CT scanner. A training set of 30 randomly selected patients was used to develop a lightweight segmentation algorithm, and the other 27 patients were used as the test set. A radiologist selected the most representative axial CT image at the L3 level for both the image series for all the patients, and three groups of observers manually annotated the skeletal muscles in the 54 CT images of the test set as the gold standard. The performance of the proposed algorithm was evaluated in terms of the Dice similarity coefficient (DSC), precision, recall, 95th percentile of the Hausdorff distance (HD95), and average surface distance (ASD). The running time of the proposed algorithm was recorded. An open source deep learning-based AutoMATICA algorithm was compared with the proposed algorithm. The inter-observer variations were also used as the reference. Results: The DSC, precision, recall, HD95, ASD, and running time were 93.2 ± 1.9% (mean ± standard deviation), 96.7 ± 2.9%, 90.0 ± 2.9%, 4.8 ± 1.3 mm, 0.8 ± 0.2 mm, and 303 ± 43 ms (on CPU) for the proposed algorithm, and 94.1 ± 4.1%, 92.7 ± 5.5%, 95.7 ± 4.0%, 7.4 ± 5.7 mm, 0.9 ± 0.6 mm, and 448 ± 40 ms (on GPU) for AutoMATICA, respectively. The differences between the proposed algorithm and the inter-observer reference were 4.7%, 1.2%, 7.9%, 3.2 mm, and 0.6 mm, respectively, for the averaged DSC, precision, recall, HD95, and ASD. Conclusion: The proposed algorithm can be used to segment skeletal muscles at the L3 level in either the plain or enhanced low-dose CT images.
format Article
id doaj-art-a6b3ac4c0d744e1bb4ad9feee8d144be
institution OA Journals
issn 2379-1381
2379-139X
language English
publishDate 2024-09-01
publisher MDPI AG
record_format Article
series Tomography
spelling doaj-art-a6b3ac4c0d744e1bb4ad9feee8d144be2025-08-20T01:55:53ZengMDPI AGTomography2379-13812379-139X2024-09-011091513152610.3390/tomography10090111Skeletal Muscle Segmentation at the Level of the Third Lumbar Vertebra (L3) in Low-Dose Computed Tomography: A Lightweight AlgorithmXuzhi Zhao0Yi Du1Haizhen Yue2School of Electronic and Information Engineering, Beijing Jiaotong University, Beijing 100044, ChinaKey Laboratory of Carcinogenesis and Translational Research (Ministry of Education/Beijing), Department of Radiation Oncology, Peking University Cancer Hospital & Institute, Beijing 100142, ChinaKey Laboratory of Carcinogenesis and Translational Research (Ministry of Education/Beijing), Department of Radiation Oncology, Peking University Cancer Hospital & Institute, Beijing 100142, ChinaBackground: The cross-sectional area of skeletal muscles at the level of the third lumbar vertebra (L3) measured from computed tomography (CT) images is an established imaging biomarker used to assess patients’ nutritional status. With the increasing prevalence of low-dose CT scans in clinical practice, accurate and automated skeletal muscle segmentation at the L3 level in low-dose CT images has become an issue to address. This study proposed a lightweight algorithm for automated segmentation of skeletal muscles at the L3 level in low-dose CT images. Methods: This study included 57 patients with rectal cancer, with both low-dose plain and contrast-enhanced pelvic CT image series acquired using a radiotherapy CT scanner. A training set of 30 randomly selected patients was used to develop a lightweight segmentation algorithm, and the other 27 patients were used as the test set. A radiologist selected the most representative axial CT image at the L3 level for both the image series for all the patients, and three groups of observers manually annotated the skeletal muscles in the 54 CT images of the test set as the gold standard. The performance of the proposed algorithm was evaluated in terms of the Dice similarity coefficient (DSC), precision, recall, 95th percentile of the Hausdorff distance (HD95), and average surface distance (ASD). The running time of the proposed algorithm was recorded. An open source deep learning-based AutoMATICA algorithm was compared with the proposed algorithm. The inter-observer variations were also used as the reference. Results: The DSC, precision, recall, HD95, ASD, and running time were 93.2 ± 1.9% (mean ± standard deviation), 96.7 ± 2.9%, 90.0 ± 2.9%, 4.8 ± 1.3 mm, 0.8 ± 0.2 mm, and 303 ± 43 ms (on CPU) for the proposed algorithm, and 94.1 ± 4.1%, 92.7 ± 5.5%, 95.7 ± 4.0%, 7.4 ± 5.7 mm, 0.9 ± 0.6 mm, and 448 ± 40 ms (on GPU) for AutoMATICA, respectively. The differences between the proposed algorithm and the inter-observer reference were 4.7%, 1.2%, 7.9%, 3.2 mm, and 0.6 mm, respectively, for the averaged DSC, precision, recall, HD95, and ASD. Conclusion: The proposed algorithm can be used to segment skeletal muscles at the L3 level in either the plain or enhanced low-dose CT images.https://www.mdpi.com/2379-139X/10/9/111skeletal musclesmuscle segmentationthird lumbar vertebra (L3)low-dose CT imagesnutritional status
spellingShingle Xuzhi Zhao
Yi Du
Haizhen Yue
Skeletal Muscle Segmentation at the Level of the Third Lumbar Vertebra (L3) in Low-Dose Computed Tomography: A Lightweight Algorithm
Tomography
skeletal muscles
muscle segmentation
third lumbar vertebra (L3)
low-dose CT images
nutritional status
title Skeletal Muscle Segmentation at the Level of the Third Lumbar Vertebra (L3) in Low-Dose Computed Tomography: A Lightweight Algorithm
title_full Skeletal Muscle Segmentation at the Level of the Third Lumbar Vertebra (L3) in Low-Dose Computed Tomography: A Lightweight Algorithm
title_fullStr Skeletal Muscle Segmentation at the Level of the Third Lumbar Vertebra (L3) in Low-Dose Computed Tomography: A Lightweight Algorithm
title_full_unstemmed Skeletal Muscle Segmentation at the Level of the Third Lumbar Vertebra (L3) in Low-Dose Computed Tomography: A Lightweight Algorithm
title_short Skeletal Muscle Segmentation at the Level of the Third Lumbar Vertebra (L3) in Low-Dose Computed Tomography: A Lightweight Algorithm
title_sort skeletal muscle segmentation at the level of the third lumbar vertebra l3 in low dose computed tomography a lightweight algorithm
topic skeletal muscles
muscle segmentation
third lumbar vertebra (L3)
low-dose CT images
nutritional status
url https://www.mdpi.com/2379-139X/10/9/111
work_keys_str_mv AT xuzhizhao skeletalmusclesegmentationatthelevelofthethirdlumbarvertebral3inlowdosecomputedtomographyalightweightalgorithm
AT yidu skeletalmusclesegmentationatthelevelofthethirdlumbarvertebral3inlowdosecomputedtomographyalightweightalgorithm
AT haizhenyue skeletalmusclesegmentationatthelevelofthethirdlumbarvertebral3inlowdosecomputedtomographyalightweightalgorithm